Visualization Lab 3

# steps 4,5, 6 use euclidean distance
library(plotly)

Question 1.

# keep columns 1,2,5,6,7,9,10,16,17,18,19
p_e <- prices_earnings[, c(1,2,5,6,7,9,10,16,17,18,19)]
rownames(p_e) <- p_e[[1]]

Question 2.

Without doing any reordering We cannot identify any clusters or outliers.

#p_e_sc %>% 
  plot_ly(x =~colnames(p_e_sc), y =~rownames(p_e_sc),
    z = ~p_e_sc, type = "heatmap", 
    colors = colorRamp(c("black","red"))
  ) %>%
  layout(title =  "Heatmap of prices and earnings",
         xaxis = list(title = "Price-Earnings Indicators", zeroline = FALSE),
         yaxis = list(title = "Cities", zeroline = FALSE)
  )

Question 3.

# seriation needs to permute rows and columns, thus distance by row and column
p_e_rdist <- dist(p_e_sc, method = "euclidean")
p_e_cdist <- dist(t(p_e_sc), method = "euclidean")

# computing distance as one minus correlation
p_e_cor <- 1 - cor(p_e_sc)
# as distance
p_e_cor_dist <- as.dist(p_e_cor)